Mistral OCR 4.1

(docs.mistral.ai)

111 points | by spelk 2 hours ago

9 comments

  • piterrro 32 minutes ago
    For anyone interested, I have an ocr pipeline running on rented GPUs, doing around 1000pages for 0.05-01 usd with around 0.8 seconds per page with full bounding boxes support for grounding.

    If you’re interested you can find contact to me via this profile.

    3.5 usd/1000 pages is just too expensive…

    • aliljet 16 minutes ago
      Accuracy is truly what people die for in the OCR game. Price isn't the primary function here.. it's an equation of price, accuracy, speed, and in mayn cases regulation.
      • merb 5 minutes ago
        Tbf even with tesseract you already get shit ton of accuracy and you can probably do these 1000 pages for way less than 3.5€. For 3.5€ you can spin up a cloud instance with 8vCPU+32gb on gcloud for 11 hours (or 11 instances for an hour) which can do way more than 1000 pages per hour on tesseract. It takes you around 6 second per page +-4 seconds start/stop depending on what you are doing on that instance size without too much optimization (you can probably even run multiple processes on a single node)
      • piterrro 4 minutes ago
        Most use cases dont need that kind of accuracy, just doesnt justify the 3-4usd range
    • x3ro 20 minutes ago
      You should put contact details in your profile :)
  • king_crimson 1 hour ago
    At this point I lost all hope for Europe playing any significant role in the AI race. If that’s a good or a bad thing I don’t know, but it seems to me like that’s the reality.
    • kubb 1 hour ago
      It's not a race. You don't get anything for winning.
      • Palpatineli 35 minutes ago
        How about "being able to align ASI somewhat to your values"?
        • ben_w 28 minutes ago
          True, but that isn't EU/US/China, it's OpenAI/Anthropic/Grok/ …/DeepMind (based in UK)/… DeepSeek

          With a lot of Chinese nationals in American companies, and an American corporation owning DeepMind, and a lot of people very upset with all of them at the same time, this is very messy.

      • procgen 56 minutes ago
        The only prize is control of the light cone.
      • bpodgursky 1 hour ago
        It's red queen. You stay alive by winning, you lose everything by losing.
        • ben_w 32 minutes ago
          Not sure you get either outcome in either case.

          Race dynamics increases p(doom) for everyone.

          The non-doom scenarios include "utopia for all", and "power flows to investors, not citizens of whichever nation the winning model's corp. was registered in".

          Independently, "oh look all the investors went bankrupt" can happen in both "doom" and "normal technology" timelines.

      • ChrisClark 49 minutes ago
        Unless you manage to build a god, and keep it under control... okay, we're all going to lose
    • thadt 1 hour ago
      Yeah? And here I've been a happy Transkribus customer for some time now. If there are better models or interfaces out there for analyzing historical handwriting, I'll definitely take a look.
  • ComputerPerson 1 hour ago
    I've got a scan from a book that I OCR with new releases. Ligatures, critical sigla, Fraktur letterforms, subscripts, superscripts, etc.

    Nothing special about this model for overly-detailed work like mine.

    It's been a while since I last tested (and discontinued my subscription), but the "pro" models from OpenAI dominate. Not surprising, given the price difference, but it would be nice if an OCR-specific model could perform better. It's worth mentioning that even the highest-end models do a pretty poor job with intricate text like mine.

    • rtaylorgarlock 1 hour ago
      Yet: how is pricing? Evaluating contents and routing appropriately isn't a new challenge in OCR, one of the oldest fields of applications in ML. Thus, how do the smaller open models perform in tandem with relatively pricy $/pg models & APIs? Your use case is remarkably rare relative to the volume and price sensitivity of enterprise data warehouse ops.
    • kmitz 22 minutes ago
      I got the opposite experience very recently : tried to OCR a bunch of handwritten emails addresses with chatGPT and I had to make so many corrections that I gave up. Whereas Mistral nailed it on first pass.
    • petcat 1 hour ago
      > the "pro" models from OpenAI dominate. Not surprising considering the price difference, but it would ne nice if an OCR-specific model could do better.

      I haven't been impressed with any of Mistral's models. They obviously realized that they couldn't compete at the frontier so they decided to go for smaller focused models but even those have not been that good.

  • merb 1 hour ago
    1000 Pages / 3.5€ this is expensive as hell. If this is not fastly superior than something like tesseract it is not worth it.
    • beernet 20 minutes ago
      Agreed. Does the GTM team there really sit together like "oh yeah, that sounds reasonable" while being totally beyond typical market prices?
  • ad_fontes 13 minutes ago
    I've been experimenting with using NuExtract this week on locally OCRing bank statements that don't have a predefined document structure. It's way better than Tesseract or a generic vision-enabled model. It runs great on a single RTX 4090 at the modest throughput I need.

    Their hosted, API-based service is something like a third of the cost of this model.

  • mainecoder 1 hour ago
    The chinese did it better, mistral is alive thanks to regulations.
    • mangecoeur 39 minutes ago
      i.e. it's one AI company that's basically guaranteed to never fail since it has a market niche guaranteed by European companies and governments.
      • petcat 34 minutes ago
        Which is also why their most recent model "Shieldstral" does nothing except monitor and moderate internet content.

        After stuff like Chat Control I think they're obviously seeing a big demand for this kind of "internet safety" technology in Europe.

    • rtaylorgarlock 1 hour ago
      I've been a bit more careful about complaining about regulations broadly due to competitive advantage, e.g. ITAR
  • Johnny_Bonk 58 minutes ago
    How does this compare to Baidu Unlimited OCR. I've been very impressed with Baidu and it's essentially free to run on a decent computer, other than electricity costs.
    • spiderfarmer 54 minutes ago
      Where do your documents go?
      • rescbr 47 minutes ago
        They go to the decent computer hosting the model, which can be yours if you pay the electricity costs
  • ianhawes 59 minutes ago
    I won't comment on accuracy, but in internal benchmarks, Mistral OCR is significantly faster than comparable APIs.
  • maz1b 57 minutes ago
    How does this compare to 4?